Summary
With store: false, the docs say to
replay a response’s output items as the next request’s input. For hosted MCP that doesn’t work: an mcp_call input
item is dropped entirely, including its arguments, output and error, unless its id names a stored response. The
model never sees an earlier MCP result, so in a multi-step agent loop it invents values from that result or calls the
tool again.
Repro (gpt-5.4, reasoning effort low, public DeepWiki MCP server, 3 trials each)
- Request with
tools: [{"type":"mcp","server_label":"deepwiki","server_url":"https://mcp.deepwiki.com/mcp","require_approval":"never"}]
and a forcedask_wiki_questioncall. Keep the output items. - Follow-up: the original user message, the output items, then
“Quote the first twelve words of the answer deepwiki returned earlier. If you can’t see it, reply UNKNOWN.”
| Follow-up | Model saw the result | input_tokens |
|---|---|---|
store: true, previous_response_id |
3/3 | 738 |
store: true, items resent with their stored ids |
3/3 | 714 |
store: false, items resent (reasoning id kept, others stripped) |
0/3 | 243 |
store: false, items resent with the mcp_call removed |
0/3 | 243 |
store: false, items resent with their ids |
0/3 | — |
store: true, mcp_call without an id |
0/3 | — |
store: false, the same text as function_call + output |
3/3 | — |
An inline mcp_call costs exactly as many input tokens as no item at all, so it is dropped before the prompt is
built. A failed call’s mcp_tool_execution_error content and the call’s arguments are dropped too. An inline
mcp_list_tools item, by contrast, is honoured: the tools aren’t listed again.
After DELETE /v1/responses/{id}, resending the stored ids returns 400 item_conflict, so storing responses only
moves the problem to day 31. Zero Data Retention organisations can’t store responses at all.
Expected
An mcp_call input item with output (or error) is shown to the model like a function_call + function_call_output
pair, whether or not it references a stored response.
Workaround in use
Each finished mcp_call is followed by an assistant message (phase: "commentary") that restates the call and its
output.